This repository is a collection of awesome things about domain generalization, including papers, code, etc.
If you would like to contribute to our repository or have any questions/advice, see Contributing & Contact.
- Awesome Domain Generalization
- Contents
- Papers
- Survey
- Theory & Analysis
- Domain Generalization
- Domain Alignment-Based Methods
- Data Augmentation-Based Methods
- Meta-Learning-Based Methods
- Ensemble Learning-Based Methods
- Self-Supervised Learning-Based Methods
- Disentangled Representation Learning-Based Methods
- Regularization-Based Methods
- Normalization-Based Methods
- Information-Based Methods
- Causality-Based Methods
- Inference-Time-Based Methods
- Neural Architecture Search-based Methods
- Single Domain Generalization
- Semi/Weak/Un-Supervised Domain Generalization
- Open/Heterogeneous Domain Generalization
- Federated Domain Generalization
- Applications
- Related Topics
- Datasets
- Libraries
- Lectures & Tutorials & Talks
- Other Resources
- Paper Index
- Contributing & Contact
- Acknowledgements
We list papers, implementation code (the unofficial code is marked with *), etc, in the order of year and from journals to conferences. Note that some papers may fall into multiple categories.
- Generalizing to Unseen Domains: A Survey on Domain Generalization [IJCAI 2021] [Slides]
- Domain Generalization in Vision: A Survey [TPAMI 2022]
We list the papers that either provide inspiring theoretical analyses or conduct extensive empirical studies for domain generalization.
- A Generalization Error Bound for Multi-Class Domain Generalization [arXiv 2019]
- Domain Generalization by Marginal Transfer Learning [JMLR 2021] [Code]
- The Risks of Invariant Risk Minimization [ICLR 2021]
- In Search of Lost Domain Generalization [ICLR 2021]
- The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization [ICCV 2021] [Code]
- An Empirical Investigation of Domain Generalization with Empirical Risk Minimizers [NeurIPS 2021] [Code]
- Towards a Theoretical Framework of Out-Of-Distribution Generalization [NeurIPS 2021]
- Out-of-Distribution Generalization in Kernel Regression [NeurIPS 2021]
- Quantifying and Improving Transferability in Domain Generalization [NeurIPS 2021] [Code]
To address the dataset/domain shift problem [108] [109] [110] [111] [112], domain generalization [113] aims to learn a model from source domain(s) and make it generalize well to unknown target domains.
Domain alignment-based methods aim to minimize divergence between source domains for learning domain-invariant representations.
- Domain Generalization via Invariant Feature Representation [ICML 2013] [Code]
- Learning Attributes Equals Multi-Source Domain Generalization [CVPR 2016]
- Robust Domain Generalisation by Enforcing Distribution Invariance [IJCAI 2016]
- Scatter Component Analysis A Unified Framework for Domain Adaptation and Domain Generalization [TPAMI 2017]
- Unified Deep Supervised Domain Adaptation and Generalization [ICCV 2017] [Code]
- Beyond Domain Adaptation: Unseen Domain Encapsulation via Universal Non-volume Preserving Models [arXiv 2018]
- Domain Generalization via Conditional Invariant Representation [AAAI 2018]
- Domain Generalization with Adversarial Feature Learning [CVPR 2018] [Code]
- Deep Domain Generalization via Conditional Invariant Adversarial Networks [ECCV 2018]
- Generalizing to Unseen Domains via Distribution Matching [arXiv 2019] [Code]
- Image Alignment in Unseen Domains via Domain Deep Generalization [arXiv 2019]
- Multi-Adversarial Discriminative Deep Domain Generalization for Face Presentation Attack Detection [CVPR 2019] [Code]
- Generalizable Feature Learning in the Presence of Data Bias and Domain Class Imbalance with Application to Skin Lesion Classification [MICCAI 2019]
- Domain Generalization via Model-Agnostic Learning of Semantic Features [NeurIPS 2019] [Code]
- Adversarial Invariant Feature Learning with Accuracy Constraint for Domain Generalization [ECMLPKDD 2019] [Code]
- Feature Alignment and Restoration for Domain Generalization and Adaptation [arXiv 2020]
- Representation via Representations: Domain Generalization via Adversarially Learned Invariant Representations [arXiv 2020]
- Feature alignment and restoration for domain generalization and adaptation [arXiv 2020]
- Correlation-aware Adversarial Domain Adaptation and Generalization [PR 2020] [Code]
- Domain Generalization Using a Mixture of Multiple Latent Domains [AAAI 2020] [Code]
- Single-Side Domain Generalization for Face Anti-Spoofing [CVPR 2020] [Code]
- Scanner Invariant Multiple Sclerosis Lesion Segmentation from MRI [ISBI 2020]
- Respecting Domain Relations: Hypothesis Invariance for Domain Generalization [ICPR 2020]
- Domain Generalization via Multidomain Discriminant Analysis [UAI 2020] [Code]
- Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization [NeurIPS 2020] [Code]
- Domain Generalization via Entropy Regularization [NeurIPS 2020] [Code]
- Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments [arXiv 2021]
- Semi-Supervised Domain Generalization in RealWorld: New Benchmark and Strong Baseline [arXiv 2021]
- Collaborative Semantic Aggregation and Calibration for Separated Domain Generalization [arXiv 2021] [Code]
- Multi-Domain Adversarial Feature Generalization for Person Re-Identification [TIP 2021]
- Scale Invariant Domain Generalization Image Recapture Detection [ICONIP 2021]
- Domain Generalization under Conditional and Label Shifts via Variational Bayesian Inference [IJCAI 2021]
- Domain Generalization using Causal Matching [ICML 2021] [Code]
- Generalization on Unseen Domains via Inference-Time Label-Preserving Target Projections [CVPR 2021] [Code]
- Progressive Domain Expansion Network for Single Domain Generalization [CVPR 2021] [Code]
- Confidence Calibration for Domain Generalization Under Covariate Shift [ICCV 2021]
- On Calibration and Out-of-domain Generalization [NeurIPS 2021]
Data augmentation-based methods augment original data and train the model on the generated data to improve model robustness.
- Certifying Some Distributional Robustness with Principled Adversarial Training [arXiv 2017] [Code]
- Generalizing across Domains via Cross-Gradient Training [ICLR 2018] [Code]
- Generalizing to Unseen Domains via Adversarial Data Augmentation [NeurIPS 2018] [Code]
- Staining Invariant Features for Improving Generalization of Deep Convolutional Neural Networks in Computational Pathology [Frontiers in Bioengineering and Biotechnology 2019]
- Multi-component Image Translation for Deep Domain Generalization [WACV 2019] [Code]
- Domain Generalization by Solving Jigsaw Puzzles [CVPR 2019] [Code]
- Addressing Model Vulnerability to Distributional Shifts Over Image Transformation Sets [ICCV 2019] [Code]
- Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization Without Accessing Target Domain Data [ICCV 2019] [Code]
- Hallucinating Agnostic Images to Generalize Across Domains [ICCV workshop 2019]
- Improving the Generalizability of Convolutional Neural Network-Based Segmentation on CMR Images [Frontiers in Cardiovascular Medicine 2020]
- Generalizing Deep Learning for Medical Image Segmentation to Unseen Domains via Deep Stacked Transformation [TMI 2020]
- Deep Domain-Adversarial Image Generation for Domain Generalisation [AAAI 2020] [Code]
- Towards Universal Representation Learning for Deep Face Recognition [CVPR 2020] [Code]
- Heterogeneous Domain Generalization via Domain Mixup [ICASSP 2020] [Code]
- Learning to Generate Novel Domains for Domain Generalization [ECCV 2020] [Code]
- Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization [ECCV 2020] [Code]
- Towards Recognizing Unseen Categories in Unseen Domains [ECCV 2020] [Code]
- Rethinking Domain Generalization Baselines [ICPR 2020]
- More is Better: A Novel Multi-view Framework for Domain Generalization [arXiv 2021]
- Semi-Supervised Domain Generalization with Stochastic StyleMatch [arXiv 2021] [Code]
- Better Pseudo-label Joint Domain-aware Label and Dual-classifier for Semi-supervised Domain Generalization [arXiv 2021]
- Out-of-domain Generalization from a Single Source: A Uncertainty Quantification Approach [arXiv 2021]
- Towards Principled Disentanglement for Domain Generalization [arXiv 2021] [Code]
- MixStyle Neural Networks for Domain Generalization and Adaptation [arXiv 2021] [Code]
- VideoDG: Generalizing Temporal Relations in Videos to Novel Domains [TPAMI 2021] [Code]
- Domain Generalization by Marginal Transfer Learning [JMLR 2021] [Code]
- Domain Generalisation with Domain Augmented Supervised Contrastive Learning [AAAI Student Abstract 2021]
- DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic Augmentation [AAAI 2021] [Code]
- Domain Generalization with Mixstyle [ICLR 2021] [Code]
- Robust and Generalizable Visual Representation Learning via Random Convolutions [ICLR 2021] [Code]
- Learning to Learn Single Domain Generalization [CVPR 2020] [Code]
- FSDR: Frequency Space Domain Randomization for Domain Generalization [CVPR 2021] [Code]
- FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space [CVPR 2021] [Code]
- Uncertainty-guided Model Generalization to Unseen Domains [CVPR 2021] [Code]
- Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning [CVPR 2021]
- A Fourier-Based Framework for Domain Generalization [CVPR 2021] [Code]
- Open Domain Generalization with Domain-Augmented Meta-Learning [CVPR 2021] [Code]
- A Simple Feature Augmentation for Domain Generalization [ICCV 2021]
- Universal Cross-Domain Retrieval Generalizing Across Classes and Domains [ICCV 2021] [Code]
- Feature Stylization and Domain-aware Contrastive Learning for Domain Generalization [MM 2021]
- Adversarial Teacher-Student Representation Learning for Domain Generalization [NeurIPS 2021]
- Model-Based Domain Generalization [NeurIPS 2021] [Code]
Meta-learning-based methods train the model on a meta-train set and improve its performance on a meta-test set for boosting out-of-domain generalization ability.
- Learning to Generalize: Meta-Learning for Domain Generalization [AAAI 2018] [Code]
- MetaReg: Towards Domain Generalization using Meta-Regularization [NeurIPS 2018] [Code*]
- Feature-Critic Networks for Heterogeneous Domain Generalisation [ICML 2019] [Code]
- Episodic Training for Domain Generalization [ICCV 2019] [Code]
- Domain Generalization via Model-Agnostic Learning of Semantic Features [NeurIPS 2019] [Code]
- Domain Generalization via Semi-supervised Meta Learning [arXiv 2020] [Code]
- Frustratingly Simple Domain Generalization via Image Stylization [arXiv 2020] [Code]
- Domain Generalization for Named Entity Boundary Detection via Metalearning [TNNLS 2020]
- Learning to Learn Single Domain Generalization [CVPR 2020] [Code]
- Learning to Learn with Variational Information Bottleneck for Domain Generalization [ECCV 2020]
- Sequential Learning for Domain Generalization [ECCV workshop 2020]
- Shape-Aware Meta-Learning for Generalizing Prostate MRI Segmentation to Unseen Domains [MICCAI 2020] [Code]
- More is Better: A Novel Multi-view Framework for Domain Generalization [arXiv 2021]
- Few-Shot Classification in Unseen Domains by Episodic Meta-Learning Across Visual Domains [ICIP 2021]
- Meta-Learned Feature Critics for Domain Generalized Semantic Segmentation [ICIP 2021]
- MetaNorm: Learning to Normalize Few-Shot Batches Across Domains [ICLR 2021] [Code]
- Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification [CVPR 2021] [Code]
- Uncertainty-guided Model Generalization to Unseen Domains [CVPR 2021] [Code]
- Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning [CVPR 2021]
- Meta Batch-Instance Normalization for Generalizable Person Re-Identification [CVPR 2021] [Code]
- Open Domain Generalization with Domain-Augmented Meta-Learning [CVPR 2021] [Code]
- Exploiting Domain-Specific Features to Enhance Domain Generalization [NeurIPS 2021] [Code]
Ensemble learning-based methods mainly train a domain-specific model on each source domain, and then draw on collective wisdom to make accurate prediction.
- Exploiting Low-Rank Structure from Latent Domains for Domain Generalization [ECCV 2014]
- Visual recognition by learning from web data: A weakly supervised domain generalization approach [CVPR 2015]
- Multi-View Domain Generalization for Visual Recognition [ICCV 2015]
- Deep Domain Generalization With Structured Low-Rank Constraint [TIP 2017]
- Visual Recognition by Learning From Web Data via Weakly Supervised Domain Generalization [TNNLS 2017]
- Robust Place Categorization with Deep Domain Generalization [IEEE Robotics and Automation Letters 2018] [Code]
- Multi-View Domain Generalization Framework for Visual Recognition [TNNLS 2018]
- Domain Generalization with Domain-Specific Aggregation Modules [GCPR 2018]
- Best Sources Forward: Domain Generalization through Source-Specific Nets [ICIP 2018]
- Batch Normalization Embeddings for Deep Domain Generalization [arXiv 2020]
- DoFE: Domain-oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasets [TMI 2020]
- MS-Net: Multi-Site Network for Improving Prostate Segmentation with Heterogeneous MRI Data [TMI 2020] [Code]
- Generalized Convolutional Forest Networks for Domain Generalization and Visual Recognition [ICLR 2020]
- Learning to Optimize Domain Specific Normalization for Domain Generalization [ECCV 2020]
- Class-conditioned Domain Generalization via Wasserstein Distributional Robust Optimization [ICLR workshop 2021]
- Domain and Content Adaptive Convolution for Domain Generalization in Medical Image Segmentation [arXiv 2021]
- Dynamically Decoding Source Domain Knowledge for Unseen Domain Generalization [arXiv 2021]
- Domain Adaptive Ensemble Learning [TIP 2021] [Code]
- Generalizable Person Re-identification with Relevance-aware Mixture of Experts [CVPR 2021]
- Learning Transferrable and Interpretable Representations for Domain Generalization [MM 2021]
- Embracing the Dark Knowledge: Domain Generalization Using Regularized Knowledge Distillation [MM 2021]
- TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification [NeurIPS 2021] [Code]
Self-supervised learning-based methods improve model generalization by solving some pretext tasks with data itself.
- Domain Generalization for Object Recognition with Multi-Task Autoencoders [ICCV 2015] [Code]
- Domain Generalization by Solving Jigsaw Puzzles [CVPR 2019] [Code]
- Improving Out-Of-Distribution Generalization via Multi-Task Self-Supervised Pretraining [arXiv 2020]
- Generalized Convolutional Forest Networks for Domain Generalization and Visual Recognition [ICLR 2020]
- Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization [ECCV 2020] [Code]
- Zero Shot Domain Generalization [BMVC 2020] [Code]
- Out-of-domain Generalization from a Single Source: A Uncertainty Quantification Approach [arXiv 2021]
- Unsupervised Domain Generalization by Learning a Bridge Across Domains [arXiv 2021]
- Self-Supervised Learning Across Domains [TPAMI 2021] [Code]
- Multi-Domain Adversarial Feature Generalization for Person Re-Identification [TIP 2021]
- Scale Invariant Domain Generalization Image Recapture Detection [ICONIP 2021]
- Domain Generalisation with Domain Augmented Supervised Contrastive Learning [AAAI Student Abstract 2021]
- Progressive Domain Expansion Network for Single Domain Generalization [CVPR 2021] [Code]
- FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space [CVPR 2021] [Code]
- Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencoder [ICCV 2021]
- A Style and Semantic Memory Mechanism for Domain Generalization [ICCV 2021]
- SelfReg: Self-Supervised Contrastive Regularization for Domain Generalization [ICCV 2021]
- Domain Generalization for Mammography Detection via Multi-style and Multi-view Contrastive Learning [MICCAI 2021] [Code]
- Feature Stylization and Domain-aware Contrastive Learning for Domain Generalization [MM 2021]
- Adversarial Teacher-Student Representation Learning for Domain Generalization [NeurIPS 2021]
Disentangled representation learning-based methods aim to disentangle domain-specific and domain-invariant parts from source data, and then adopt the domain-invariant one for inference on the target domains.
- Undoing the Damage of Dataset Bias [ECCV 2012] [Code]
- Deeper, Broader and Artier Domain Generalization [ICCV 2017] [Code]
- DIVA: Domain Invariant Variational Autoencoders [ICML workshop 2019] [Code]
- Efficient Domain Generalization via Common-Specific Low-Rank Decomposition [ICML 2020] [Code]
- Cross-Domain Face Presentation Attack Detection via Multi-Domain Disentangled Representation Learning [CVPR 2020]
- Learning to Balance Specificity and Invariance for In and Out of Domain Generalization [ECCV 2020] [Code]
- Towards Principled Disentanglement for Domain Generalization [arXiv 2021] [Code]
- Meta-Learned Feature Critics for Domain Generalized Semantic Segmentation [ICIP 2021]
- DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic Augmentation [AAAI 2021] [Code]
- Robustnet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening [CVPR 2021] [Code]
- Shape-Biased Domain Generalization via Shock Graph Embeddings [ICCV 2021]
- Domain-Invariant Disentangled Network for Generalizable Object Detection [ICCV 2021]
- Domain Generalization via Feature Variation Decorrelation [MM 2021]
- Exploiting Domain-Specific Features to Enhance Domain Generalization [NeurIPS 2021] [Code]
Regularization-based methods leverage regularization terms to prevent the overfitting, or design optimization strategies to guide the training.
- Generalizing from Several Related Classification Tasks to a New Unlabeled Sample [NeurIPS 2011]
- MetaReg: Towards Domain Generalization using Meta-Regularization [NeurIPS 2018] [Code*]
- Invariant Risk Minimization [arXiv 2019] [Code]
- Learning Robust Representations by Projecting Superficial Statistics Out [ICLR 2019] [Code]
- Self-challenging Improves Cross-Domain Generalization [ECCV 2020] [Code]
- Energy-based Out-of-distribution Detection [NeurIPS 2020] [Code]
- Fishr: Invariant Gradient Variances for Our-of-distribution Generalization [arXiv 2021] [Code]
- Out-of-Distribution Generalization via Risk Extrapolation [ICML 2021]
- A Fourier-Based Framework for Domain Generalization [CVPR 2021] [Code]
- Domain Generalization via Gradient Surgery [ICCV 2021] [Code]
- SelfReg: Self-Supervised Contrastive Regularization for Domain Generalization [ICCV 2021]
- Embracing the Dark Knowledge: Domain Generalization Using Regularized Knowledge Distillation [MM 2021]
- Model-Based Domain Generalization [NeurIPS 2021] [Code]
- Swad: Domain Generalization by Seeking Flat Minima [NeurIPS 2021] [Code]
- Training for the Future: A Simple Gradient Interpolation Loss to Generalize Along Time [NeurIPS 2021] [Code]
- Quantifying and Improving Transferability in Domain Generalization [NeurIPS 2021] [Code]
Normalization-based methods calibrate data from different domains by normalizing them with their statistic.
- Batch Normalization Embeddings for Deep Domain Generalization [arXiv 2020]
- Learning to Optimize Domain Specific Normalization for Domain Generalization [ECCV 2020]
- MetaNorm: Learning to Normalize Few-Shot Batches Across Domains [ICLR 2021] [Code]
- Meta Batch-Instance Normalization for Generalizable Person Re-Identification [CVPR 2021] [Code]
- Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification [CVPR 2021] [Code]
- Adversarially Adaptive Normalization for Single Domain Generalization [CVPR 2021]
- Collaborative Optimization and Aggregation for Decentralized Domain Generalization and Adaptation [ICCV 2021]
- Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition [WACV 2022]
Information-based methods utilize techniques of information theory to realize domain generalization.
- Learning to Learn with Variational Information Bottleneck for Domain Generalization [ECCV 2020]
- Progressive Domain Expansion Network for Single Domain Generalization [CVPR 2021] [Code]
- Learning To Diversify for Single Domain Generalization [ICCV 2021] [Code]
- Invariance Principle Meets Information Bottleneck for Out-Of-Distribution Generalization [NeurIPS 2021] [Code]
- Exploiting Domain-Specific Features to Enhance Domain Generalization [NeurIPS 2021] [Code]
- Invariant Information Bottleneck for Domain Generalization [AAAI 2022] [Code]
Causality-based methods analyze and address the domain generalization problem from a causal perspective.
- Invariant Risk Minimization [arXiv 2019] [Code]
- Learning Domain-Invariant Relationship with Instrumental Variable for Domain Generalization [arXiv 2021]
- A Causal Framework for Distribution Generalization [TPAMI 2021] [Code]
- Domain Generalization using Causal Matching [ICML 2021] [Code]
- Deep Stable Learning for Out-of-Distribution Generalization [CVPR 2021] [Code]
- A Style and Semantic Memory Mechanism for Domain Generalization [ICCV 2021]
- Learning Causal Semantic Representation for Out-of-Distribution Prediction [NeurIPS 2021] [Code]
- Recovering Latent Causal Factor for Generalization to Distributional Shifts [NeurIPS 2021] [Code]
- On Calibration and Out-of-domain Generalization [NeurIPS 2021]
- Invariance Principle Meets Information Bottleneck for Out-Of-Distribution Generalization [NeurIPS 2021] [Code]
- Invariant Information Bottleneck for Domain Generalization [AAAI 2022] [Code]
Inference-time-based methods leverage the unlabeled target data, which is available at inference-time, to improve generalization performance without further model training.
- Generalization on Unseen Domains via Inference-Time Label-Preserving Target Projections [CVPR 2021] [Code]
- Adaptive Methods for Real-World Domain Generalization [CVPR 2021] [Code]
- Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization [NeurIPS 2021] [Code]
Neural architecture search-based methods aim to dynamically tune the network architecture to improve out-of-domain generalization.
- NAS-OoD Neural Architecture Search for Out-of-Distribution Generalization [ICCV 2021]
The goal of single domain generalization task is to improve model performance on unknown target domains by using data from only one source domain.
- Learning to Learn Single Domain Generalization [CVPR 2020] [Code]
- Out-of-domain Generalization from a Single Source: A Uncertainty Quantification Approach [arXiv 2021]
- Uncertainty-guided Model Generalization to Unseen Domains [CVPR 2021] [Code]
- Adversarially Adaptive Normalization for Single Domain Generalization [CVPR 2021]
- Progressive Domain Expansion Network for Single Domain Generalization [CVPR 2021] [Code]
- Learning To Diversify for Single Domain Generalization [ICCV 2021] [Code]
Semi/weak-supervised domain generalization assumes that a part of the source data is unlabeled, while unsupervised domain generalization assumes no training supervision.
- Visual recognition by learning from web data: A weakly supervised domain generalization approach [CVPR 2015]
- Visual Recognition by Learning From Web Data via Weakly Supervised Domain Generalization [TNNLS 2017]
- Domain Generalization via Semi-supervised Meta Learning [arXiv 2020] [Code]
- Deep Semi-supervised Domain Generalization Network for Rotary Machinery Fault Diagnosis under Variable Speed [IEEE Transactions on Instrumentation and Measurement 2020]
- Semi-Supervised Domain Generalization with Stochastic StyleMatch [arXiv 2021] [Code]
- Better Pseudo-label Joint Domain-aware Label and Dual-classifier for Semi-supervised Domain Generalization [arXiv 2021]
- Semi-Supervised Domain Generalization in RealWorld: New Benchmark and Strong Baseline [arXiv 2021]
- Unsupervised Domain Generalization by Learning a Bridge Across Domains [arXiv 2021]
- Domain-Specific Bias Filtering for Single Labeled Domain Generalization [arXiv 2021] [Code]
Open/heterogeneous domain generalization assumes the label space of one domain is different from that of another domain.
- Feature-Critic Networks for Heterogeneous Domain Generalisation [ICML 2019] [Code]
- Episodic Training for Domain Generalization [ICCV 2019] [Code]
- Towards Recognizing Unseen Categories in Unseen Domains [ECCV 2020] [Code]
- Heterogeneous Domain Generalization via Domain Mixup [ICASSP 2020] [Code]
- Open Domain Generalization with Domain-Augmented Meta-Learning [CVPR 2021] [Code]
- Universal Cross-Domain Retrieval Generalizing Across Classes and Domains [ICCV 2021] [Code]
Federated domain generalization assumes that source data is distributed and can not be fused for data privacy protection.
- Collaborative Semantic Aggregation and Calibration for Separated Domain Generalization [arXiv 2021] [Code]
- FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space [CVPR 2021] [Code]
- Collaborative Optimization and Aggregation for Decentralized Domain Generalization and Adaptation [ICCV 2021]
- Deep Domain-Adversarial Image Generation for Domain Generalisation [AAAI 2020] [Code]
- Learning to Generate Novel Domains for Domain Generalization [ECCV 2020] [Code]
- Learning Generalisable Omni-Scale Representations for Person Re-Identification [TPAMI 2021] [Code]
- Multi-Domain Adversarial Feature Generalization for Person Re-Identification [TIP 2021]
- Domain Generalization with Mixstyle [ICLR 2021] [Code]
- Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification [CVPR 2021] [Code]
- Meta Batch-Instance Normalization for Generalizable Person Re-Identification [CVPR 2021] [Code]
- Generalizable Person Re-identification with Relevance-aware Mixture of Experts [CVPR 2021]
- TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification [NeurIPS 2021] [Code]
- Multi-Adversarial Discriminative Deep Domain Generalization for Face Presentation Attack Detection [CVPR 2019] [Code]
- Towards Universal Representation Learning for Deep Face Recognition [CVPR 2020] [Code]
- Cross-Domain Face Presentation Attack Detection via Multi-Domain Disentangled Representation Learning [CVPR 2020]
- Single-Side Domain Generalization for Face Anti-Spoofing [CVPR 2020] [Code]
- Sequential Learning for Domain Generalization [ECCV workshop 2020]
- Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning [CVPR 2021]
Evaluations on the following datasets often follow leave-one-domain-out protocol: randomly choose one domain to hold out as the target domain, while the others are used as the source domain(s).
Datasets (download link) | Description | Related papers in Paper Index |
---|---|---|
Colored MNIST [165] | Handwritten digit recognition; 3 domains: {0.1, 0.3, 0.9}; 70,000 samples of dimension (2, 28, 28); 2 classes | [82], [138], [140], [149], [152], [154], [165], [171], [173], [190], [200], [202] |
Rotated MNIST [6] (original) | Handwritten digit recognition; 6 domains with rotated degree: {0, 15, 30, 45, 60, 75}; 7,000 samples of dimension (1, 28, 28); 10 classes | [5], [6], [15], [35], [53], [55], [63], [71], [73], [74], [76], [77], [86], [90], [105], [107], [138], [140], [170], [173], [202], [204], [206] |
Digits-DG [28] | Handwritten digit recognition; 4 domains: {MNIST [29], MNIST-M [30], SVHN [31], SYN [30]}; 24,000 samples; 10 classes | [21], [25], [27], [28], [34], [35], [55], [59], [63], [69], [94], [98], [116], [118], [130], [141], [142], [146], [151], [153], [157], [158], [159], [160], [166], [168], [179], [189], [203] |
VLCS [16] (1; or original) | Object recognition; 4 domains: {Caltech [8], LabelMe [9], PASCAL [10], SUN [11]}; 10,729 samples of dimension (3, 224, 224); 5 classes; about 3.6 GB | [2], [6], [7], [14], [15], [18], [60], [61], [64], [67], [68], [70], [71], [74], [76], [77], [81], [83], [86], [91], [98], [99], [101], [102], [103], [117], [118], [126], [127], [131], [132], [136], [138], [140], [142], [145], [146], [148], [149], [161], [170], [173], [174], [184], [190], [195], [199], [201], [202], [203] |
Office31+Caltech [32] (1) | Object recognition; 4 domains: {Amazon, Webcam, DSLR, Caltech}; 4,652 samples in 31 classes (office31) or 2,533 samples in 10 classes (office31+caltech); 51 MB | [6], [35], [67], [68], [70], [71], [80], [91], [96], [119], [131], [167] |
OfficeHome [20] (1; or original) | Object recognition; 4 domains: {Art, Clipart, Product, Real World}; 15,588 samples of dimension (3, 224, 224); 65 classes; 1.1 GB | [19], [54], [28], [34], [55], [58], [60], [61], [64], [69], [80], [92], [94], [98], [101], [118], [126], [130], [131], [132], [133], [137], [138], [140], [146], [148], [156], [159], [160], [162], [163], [167], [173], [174], [178], [179], [184], [189], [190], [199], [201], [202], [203], [206] |
PACS [2] (1; or original) | Object recognition; 4 domains: {photo, art_painting, cartoon, sketch}; 9,991 samples of dimension (3, 224, 224); 7 classes; 174 MB | [1], [2], [4], [5], [14], [15], [18], [19], [34], [54], [28], [35], [55], [56], [57], [58], [59], [60], [61], [64], [69], [73], [77], [80], [81], [82], [83], [84], [86], [90], [92], [94], [96], [98], [99], [101], [102], [104], [105], [116], [117], [118], [127], [129], [130], [131], [132], [136], [137], [138], [139], [140], [142], [145], [146], [148], [149], [153], [156], [157], [158], [159], [160], [161], [162], [163], [167], [170], [171], [173], [174], [178], [179], [180], [184], [189], [190], [195], [199], [200], [201], [202], [203], [206] |
DomainNet [33] (clipart, infograph, painting, quick-draw, real, and sketch; or original) | Object recognition; 6 domains: {clipart, infograph, painting, quick-draw, real, sketch}; 586,575 samples of dimension (3, 224, 224); 345 classes; 1.2 GB + 4.0 GB + 3.4 GB + 439 MB + 5.6 GB + 2.5 GB | [34], [57], [104], [119], [130], [131], [132], [133], [138], [140], [150], [173], [178], [189], [201], [202], [203] |
mini-DomainNet [34] | Object recognition; a smaller and less noisy version of DomainNet; 4 domains: {clipart, painting, real, sketch}; 140,006 samples | [34], [69], [130], [156], [157] |
ImageNet-Sketch [35] | Object recognition; 2 domains: {real, sketch}; 50,000 samples | [64] |
VisDA-17 [36] | Object recognition; 3 domains of synthetic-to-real generalization; 280,157 samples | [119], [178] |
CIFAR-10-C / CIFAR-100-C / ImageNet-C [37] (original) | Object recognition; the test data are damaged by 15 corruptions (each with 5 intensity levels) drawn from 4 categories (noise, blur, weather, and digital); 60,000/60,000/1.3M samples | [27], [74], [116], [141], [151], [168] |
Visual Decathlon (VD) [38] | Object/action/handwritten/digit recognition; 10 domains from the combination of 10 datasets; 1,659,142 samples | [5], [7], [128] |
IXMAS [39] | Action recognition; 5 domains with 5 camera views, 10 subjects, and 5 actions; 1,650 samples | [7], [14], [67], [76] |
SYNTHIA [42] | Semantic segmentation; 15 domains with 4 locations and 5 weather conditions; 2,700 samples | [27], [62], [115], [141], [151], [185], [193] |
GTA5-Cityscapes [43], [44] | Semantic segmentation; 2 domains of synthetic-to-real generalization; 29,966 samples | [62], [115], [185], [193] |
Terra Incognita (TerraInc) [45] (1 and 2; or original) | Animal classification; 4 domains captured at different geographical locations: {L100, L38, L43, L46}; 24,788 samples of dimension (3, 224, 224); 10 classes; 6.0 GB + 8.6 MB | [132], [136], [138], [140], [173], [201], [202], [207] |
Market-Duke [46], [47] | Person re-idetification; cross-dataset re-ID; heterogeneous DG with 2 domains; 69,079 samples | [12], [13], [28], [55], [56], [58], [114], [144], [187], [208] |
We list the GitHub libraries of domain generalization (sorted by stars).
- DeepDG (jindongwang): Deep Domain Generalization Toolkit.
- Transfer Learning Library (thuml) for Domain Adaptation, Task Adaptation, and Domain Generalization.
- DomainBed (facebookresearch) [134] is a suite to test domain generalization algorithms.
- Dassl (KaiyangZhou): A PyTorch toolbox for domain adaptation, semi-supervised learning, and domain generalization.
- (Talk 2021) Generalizing to Unseen Domains: A Survey on Domain Generalization [155]. [Video] [Slides] (Jindong Wang (MSRA), in Chinese)
- A collection of domain generalization papers organized by amber0309.
- A collection of domain generalization papers organized by jindongwang.
- A collection of papers on domain generalization, domain adaptation, causality, robustness, prompt, optimization, generative model, etc, organized by yfzhang114.
- Adaptation and Generalization Across Domains in Visual Recognition with Deep Neural Networks [PhD 2020, Kaiyang Zhou (University of Surrey)]
We list all the papers for quick check, including method abbreviation, keywords, etc.
Top Conference | Papers | Top Conference | Papers |
---|---|---|---|
before 2014 | [8], [11], [16], [31], [32], [41], [65], [87], [103], [113] | CVPR 2015 | [89] |
ICML 2015 | [30] | ICCV 2015 | [6], [46], [88] |
CVPR 2016 | [42], [44], [120] | IJCAI 2016 | [66] |
ECCV 2016 | [43], [47] | ICLR 2017 | [37] |
CVPR 2017 | [20] | ICCV 2017 | [2], [71] |
NeurIPS 2017 | [38] | AAAI 2018 | [1], [68] |
ICLR 2018 | [53] | CVPR 2018 | [76] |
ECCV 2018 | [45], [77] | NeurIPS 2018 | [4], [25] |
ICLR 2019 | [35] | CVPR 2019 | [78], [98] |
ICML 2019 | [5], [107], [110] | ICCV 2019 | [7], [21], [33], [62], [63] |
NeurIPS 2019 | [18] | AAAI 2020 | [55], [83] |
ICLR 2020 | [126] | CVPR 2020 | [22], [27], [79], [106] |
ICML 2020 | [105] | ECCV 2020 | [14], [15], [28], [57], [64], [94], [99], [104] |
NeurIPS 2020 | [75], [86], [112], [181] | ICLR 2021 | [19], [56], [59], [134], [175], [196] |
AAAI 2021 | [139], [171] | CVPR 2021 | [12], [13], [115], [116], [117], [118], [119], [132], [141], [147], [153], [160], [168], [187], [193] |
IJCAI 2021 | [155], [195] | ICML 2021 | [73], [190] |
ICCV 2021 | [129], [130], [133], [135], [138], [142], [143], [148], [149], [150], [158], [159], [194] | MM 2021 | [131], [137], [146], [157] |
NeurIPS 2021 | [136], [145], [152], [154], [198], [199], [200], [201], [202], [203], [204], [205], [206], [207], [208] | AAAI 2022 | [140] |
Top Journal | Papers |
---|---|
before 2014 | [9] (IJCV), [10] (IJCV) |
2017 | [67] (TPAMI), [91] (TIP) |
2021 | [34] (TIP), [144] (TIP), [101] (TPAMI), [114] (TPAMI), [191] (TPAMI), [197] (TPAMI), [188] (JMLR) |
arXiv | Papers |
---|---|
before 2014 | [40] |
2017 | [36], [52] |
2018 | [166] |
2019 | [81], [123], [165], [169] |
2020 | [60], [69], [82], [96], [102], [127], [189] |
2021 | [3], [54], [58], [151], [156], [161], [162], [163], [170], [173], [174], [176], [178], [179], [182], [184], [192] |
Else | Papers |
---|---|
before 2018 | [29], [39], [48], [49], [50], [51], [90], [92], [97], [109], [111], [121], [122] |
2019 | [26], [72], [84], [108], [167] |
2020 | [17], [23], [24], [61], [70], [74], [80], [85], [93], [95], [100], [124], [125], [128], [164] |
2021 | [172], [177], [180], [183], [185] |
2022 | [186] |
[1] Learning to Generalize: Meta-Learning for Domain Generalization [AAAI 2018] [Code] (MLDG, meta-learning)
[2] Deeper, Broader and Artier Domain Generalization [ICCV 2017] [Code] (disentangled representation learning, PACS dataset)
[3] Domain Generalization in Vision: A Survey [TPAMI 2022] (survey)
[4] MetaReg: Towards Domain Generalization using Meta-Regularization [NeurIPS 2018] [Code*] (MetaReg, meta-learning, regularization)
[5] Feature-Critic Networks for Heterogeneous Domain Generalisation [ICML 2019] [Code] (Feature-Critic, meta-learning, open/heterogeneous domain generalization)
[6] Domain Generalization for Object Recognition with Multi-Task Autoencoders [ICCV 2015] [Code] (MTAE, self-supervised learning, Rotated MNIST dataset)
[7] Episodic Training for Domain Generalization [ICCV 2019] [Code] (Epi-FCR, meta-learning, open/heterogeneous domain generalization)
[8] Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories [CVPR workshop 2004] (Caltech dataset)
[9] Labelme: A Database and Web-Based Tool for Image Annotation [IJCV 2008] (LabelMe dataset)
[10] The pascal visual object classes (voc) challenge [IJCV 2010] (PASCAL dataset)
[11] Sun Database: Large-Scale Scene Recognition from Abbey to Zoo [CVPR 2010] (Sun dataset)
[12] Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification [CVPR 2021] [Code] (M3L, meta-learning, normalization, person re-identification)
[13] Meta Batch-Instance Normalization for Generalizable Person Re-Identification [CVPR 2021] [Code] (MetaBIN, meta-learning, normalization, person re-identification)
[14] Sequential Learning for Domain Generalization [ECCV workshop 2020] (S-MLDG, meta-learning, life-long learning)
[15] Learning to Learn with Variational Information Bottleneck for Domain Generalization [ECCV 2020] (MetaVIB, meta-learning, information)
[16] Unbiased Metric Learning: On the Utilization of Multiple Datasets and Web Images for Softening Bias [ICCV 2013] (VLCS dataset)
[17] Shape-Aware Meta-Learning for Generalizing Prostate MRI Segmentation to Unseen Domains [MICCAI 2020] [Code] (SAML, meta-learning)
[18] Domain Generalization via Model-Agnostic Learning of Semantic Features [NeurIPS 2019] [Code] (MASF, domain alignment, meta-learning)
[19] MetaNorm: Learning to Normalize Few-Shot Batches Across Domains [ICLR 2021] [Code] (MetaNorm, meta-learning, normalization)
[20] Deep Hashing Network for Unsupervised Domain Adaptation [CVPR 2017] [Code] (OfficeHome dataset)
[21] Addressing Model Vulnerability to Distributional Shifts Over Image Transformation Sets [ICCV 2019] [Code] (data augmentation)
[22] Towards Universal Representation Learning for Deep Face Recognition [CVPR 2020] [Code] (data augmentation, face recognition & anti-spoofing)
[23] Generalizing Deep Learning for Medical Image Segmentation to Unseen Domains via Deep Stacked Transformation [TMI 2020] (BigAug, data augmentation)
[24] Improving the Generalizability of Convolutional Neural Network-Based Segmentation on CMR Images [Frontiers in Cardiovascular Medicine 2020] (data augmentation)
[25] Generalizing to Unseen Domains via Adversarial Data Augmentation [NeurIPS 2018] [Code] (data augmentation)
[26] Staining Invariant Features for Improving Generalization of Deep Convolutional Neural Networks in Computational Pathology [Frontiers in Bioengineering and Biotechnology 2019] (data augmentation)
[27] Learning to Learn Single Domain Generalization [CVPR 2020] [Code] (M-ADA, data augmentation, meta-learning, single domain generalization)
[28] Learning to Generate Novel Domains for Domain Generalization [ECCV 2020] [Code] (L2A-OT, data augmentation, person re-identification, Digits-DG dataset)
[29] Gradient-Based Learning Applied to Document Recognition [IEEE 1998] (MNIST dataset)
[30] Unsupervised Domain Adaptation by Backpropagation [ICML 2015] (MNIST-M dataset)
[31] Reading Digits in Natural Images with Unsupervised Feature Learning [NeurIPS workshop 2011] (SVHN dataset)
[32] Adapting Visual Category Models to New Domains [ECCV 2010] (Office31 dataset)
[33] Moment Matching for Multi-Source Domain Adaptation [ICCV 2019] (DomainNet dataset)
[34] Domain Adaptive Ensemble Learning [TIP 2021] [Code] (ensemble learning, mini-DomainNet dataset)
[35] Learning Robust Representations by Projecting Superficial Statistics Out [ICLR 2019] [Code] (HEX, ImageNet-Sketch dataset, regularization)
[36] Visda: The visual domain adaptation challenge [arXiv 2017] (Visda dataset)
[37] Benchmarking Neural Network Robustness to Common Corruptions and Perturbations [ICLR 2019] (CIFAR-10-C, CIFAR-100-C, ImageNet-C datasets)
[38] Learning Multiple Visual Domains with Residual Adapters [NeurIPS 2017] (Visual Decathlon dataset)
[39] Free Viewpoint Action Recognition Using Mmotion History Volumes [CVIU 2006] (IXMAS dataset)
[40] Ucf101: A dataset of 101 Human Actions Classes from Videos in the Wild [arXiv 2012] (UCF-HMDB dataset)
[41] Hmdb: Large Video Database for Human Motion Recognition [ICCV 2011] (UCF-HMDB dataset)
[42] The Synthia Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes [CVPR 2016] (SYNTHIA dataset)
[43] Playing for Data: Ground Truth from Computer Games [ECCV 2016] (GTA5-Cityscapes dataset)
[44] The Cityscapes Dataset for Semantic Urban Scene Understanding [CVPR 2016] (GTA5-Cityscapes dataset)
[45] Recognition in Terra Incognita [ECCV 2018] (TerraInc dataset)
[46] Scalable Person Re-Identification: A Benchmark [ICCV 2015] (Market-Duke dataset)
[47] Performance Measures and a Data Set for Multi-target, Multi-Camera Tracking [ECCV 2016] (Market-Duke dataset)
[48] A Face Antispoofing Database with Diverse Attacks [ICB 2012] (COMI dataset)
[49] Oulu-npu: A Mobile Face Presentation Attack Database with Realworld Variations [FG 2017] (COMI dataset)
[50] Face Spoof Detection with Image Distortion Analysis [TIFS 2015] (COMI dataset)
[51] On the Effectiveness of Local Binary Patterns in Face Anti-Spoofing [BIOSIG 2012] (COMI dataset)
[52] Certifying Some Distributional Robustness with Principled Adversarial Training [arXiv 2017] [Code] (data augmentation)
[53] Generalizing across Domains via Cross-Gradient Training [ICLR 2018] [Code] (CrossGrad, data augmentation)
[54] Semi-Supervised Domain Generalization with Stochastic StyleMatch [arXiv 2021] [Code] (StyleMatch, data augmentation, semi/weak/un-supervised domain generalization)
[55] Deep Domain-Adversarial Image Generation for Domain Generalisation [AAAI 2020] [Code] (DDAIG, data augmentation, person re-identification)
[56] Domain Generalization with Mixstyle [ICLR 2021] [Code] (MixStyle, data augmentation, person re-identification)
[57] Towards Recognizing Unseen Categories in Unseen Domains [ECCV 2020] [Code] (CuMix, data augmentation, open/heterogeneous domain generalization)
[58] MixStyle Neural Networks for Domain Generalization and Adaptation [arXiv 2021] [Code] (MixStyle, data augmentation)
[59] Robust and Generalizable Visual Representation Learning via Random Convolutions [ICLR 2021] [Code] (RC, data augmentation)
[60] Frustratingly Simple Domain Generalization via Image Stylization [arXiv 2020] [Code] (data augmentation)
[61] Rethinking Domain Generalization Baselines [ICPR 2020] (data augmentation)
[62] Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization Without Accessing Target Domain Data [ICCV 2019] [Code] (data augmentation)
[63] Hallucinating Agnostic Images to Generalize Across Domains [ICCV workshop 2019] [Code] (data augmentation)
[64] Self-challenging Improves Cross-Domain Generalization [ECCV 2020] [Code] (RSC, regularization)
[65] Domain Generalization via Invariant Feature Representation [ICML 2013] [Code] (DICA, domain alignment)
[66] Robust Domain Generalisation by Enforcing Distribution Invariance [IJCAI 2016] (ESRand, domain alignment)
[67] Scatter Component Analysis A Unified Framework for Domain Adaptation and Domain Generalization [TPAMI 2017] (SCA, domain alignment)
[68] Domain Generalization via Conditional Invariant Representation [AAAI 2018] (CIDG, domain alignment)
[69] Feature alignment and restoration for domain generalization and adaptation [arXiv 2020] (FAR, domain alignment)
[70] Domain Generalization via Multidomain Discriminant Analysis [UAI 2020] [Code] (MDA, domain alignment)
[71] Unified Deep Supervised Domain Adaptation and Generalization [ICCV 2017] [Code] (CCSA, domain alignment)
[72] Generalizable Feature Learning in the Presence of Data Bias and Domain Class Imbalance with Application to Skin Lesion Classification [MICCAI 2019] (domain alignment)
[73] Domain Generalization using Causal Matching [ICML 2021] [Code] (MatchDG, domain alignment, causality)
[74] Respecting Domain Relations: Hypothesis Invariance for Domain Generalization [ICPR 2020] (HIR, domain alignment)
[75] Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization [NeurIPS 2020] [Code] (LDDG, domain alignment)
[76] Domain Generalization with Adversarial Feature Learning [CVPR 2018] [Code] (MMD-AAE, domain alignment)
[77] Deep Domain Generalization via Conditional Invariant Adversarial Networks [ECCV 2018] (CIDDG, domain alignment)
[78] Multi-Adversarial Discriminative Deep Domain Generalization for Face Presentation Attack Detection [CVPR 2019] [Code] (MADDG, domain alignment, face recognition & anti-spoofing)
[79] Single-Side Domain Generalization for Face Anti-Spoofing [CVPR 2020] [Code] (SSDG, domain alignment, face recognition & anti-spoofing)
[80] Correlation-aware Adversarial Domain Adaptation and Generalization [PR 2020] [Code] (CAADA, domain alignment)
[81] Generalizing to Unseen Domains via Distribution Matching [arXiv 2019] [Code] (G2DM, domain alignment)
[82] Representation via Representations: Domain Generalization via Adversarially Learned Invariant Representations [arXiv 2020] (RVR, domain alignment)
[83] Domain Generalization Using a Mixture of Multiple Latent Domains [AAAI 2020] [Code] (domain alignment)
[84] Adversarial Invariant Feature Learning with Accuracy Constraint for Domain Generalization [ECMLPKDD 2019] [Code] (AFLAC, domain alignment)
[85] Scanner Invariant Multiple Sclerosis Lesion Segmentation from MRI [ISBI 2020] (domain alignment)
[86] Domain Generalization via Entropy Regularization [NeurIPS 2020] [Code] (domain alignment)
[87] Exploiting Low-Rank Structure from Latent Domains for Domain Generalization [ECCV 2014] (ensemble learning)
[88] Multi-View Domain Generalization for Visual Recognition [ICCV 2015] (MVDG, ensemble learning)
[89] Visual recognition by learning from web data: A weakly supervised domain generalization approach [CVPR 2015] (ensemble learning, semi/weak/un-supervised domain generalization)
[90] Best Sources Forward: Domain Generalization through Source-Specific Nets [ICIP 2018] (ensemble learning)
[91] Deep Domain Generalization With Structured Low-Rank Constraint [TIP 2017] (ensemble learning)
[92] Domain Generalization with Domain-Specific Aggregation Modules [GCPR 2018] (D-SAMs, ensemble learning)
[93] DoFE: Domain-oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasets [TMI 2020] (DoFE, ensemble learning)
[94] Learning to Optimize Domain Specific Normalization for Domain Generalization [ECCV 2020] (DSON, ensemble learning, normalization)
[95] MS-Net: Multi-Site Network for Improving Prostate Segmentation with Heterogeneous MRI Data [TMI 2020] [Code] (MS-Net, ensemble learning)
[96] Batch Normalization Embeddings for Deep Domain Generalization [arXiv 2020] (BNE, ensemble learning, normalization)
[97] Robust Place Categorization with Deep Domain Generalization [IEEE Robotics and Automation Letters 2018] [Code] (COLD, ensemble learning)
[98] Domain Generalization by Solving Jigsaw Puzzles [CVPR 2019] [Code] (JiGen, data augmentation, self-supervised learning)
[99] Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization [ECCV 2020] [Code] (EISNet, data augmentation, self-supervised learning)
[100] Zero Shot Domain Generalization [BMVC 2020] [Code] (self-supervised learning)
[101] Self-Supervised Learning Across Domains [TPAMI 2021] [Code] (self-supervised learning)
[102] Improving Out-Of-Distribution Generalization via Multi-Task Self-Supervised Pretraining [arXiv 2020] (self-supervised learning)
[103] Undoing the Damage of Dataset Bias [ECCV 2012] [Code] (disentangled representation learning)
[104] Learning to Balance Specificity and Invariance for In and Out of Domain Generalization [ECCV 2020] [Code] (DMG, disentangled representation learning)
[105] Efficient Domain Generalization via Common-Specific Low-Rank Decomposition [ICML 2020] [Code] (CSD, disentangled representation learning)
[106] Cross-Domain Face Presentation Attack Detection via Multi-Domain Disentangled Representation Learning [CVPR 2020] (disentangled representation learning, face recognition/antispoofing)
[107] DIVA: Domain Invariant Variational Autoencoders [ICML workshop 2019] [Code] (DIVA, disentangled representation learning)
[108] Dataset Shift in Machine Learning [MIT 2019] (dataset shift)
[109] A Unifying View on Dataset Shift in Classification [PR 2012] (dataset shift)
[110] Do Imagenet Classifiers Generalize to Imagenet? [ICML 2019] (dataset shift)
[111] A Theory of Learning from Different Domains [ML 2010] (dataset shift)
[112] Measuring Robustness to Natural Distribution Shifts in Image Classification [NeurIPS 2020] [Code] (dataset shift)
[113] Generalizing from Several Related Classification Tasks to a New Unlabeled Sample [NeurIPS 2011] (domain generalization)
[114] Learning Generalisable Omni-Scale Representations for Person Re-Identification [TPAMI 2021] [Code] (person re-identification)
[115] FSDR: Frequency Space Domain Randomization for Domain Generalization [CVPR 2021] [Code] (FSDR, data augmentation)
[116] Adversarially Adaptive Normalization for Single Domain Generalization [CVPR 2021] (ASR, normalization, single domain generalization)
[117] Deep Stable Learning for Out-of-Distribution Generalization [CVPR 2021] [Code] (StableNet, causality)
[118] Generalization on Unseen Domains via Inference-Time Label-Preserving Target Projections [CVPR 2021] [Code] (domain alignment, inference-time)
[119] Open Domain Generalization with Domain-Augmented Meta-Learning [CVPR 2021] [Code] (DAML, data augmentation, meta-learning, open/heterogeneous domain generalization)
[120] Learning Attributes Equals Multi-Source Domain Generalization [CVPR 2016] (UDICA, domain alignment)
[121] Visual Recognition by Learning From Web Data via Weakly Supervised Domain Generalization [TNNLS 2017] (ensemble learning, semi/weak/un-supervised domain generalization)
[122] Multi-View Domain Generalization Framework for Visual Recognition [TNNLS 2018] (ensemble learning)
[123] A Generalization Error Bound for Multi-Class Domain Generalization [arXiv 2019] (theory & analysis)
[124] Domain Generalization for Named Entity Boundary Detection via Metalearning [TNNLS 2020] (METABDRY, meta-learning)
[125] Deep Semi-supervised Domain Generalization Network for Rotary Machinery Fault Diagnosis under Variable Speed [IEEE Transactions on Instrumentation and Measurement 2020] (DSDGN, semi/weak/un-supervised domain generalization)
[126] Generalized Convolutional Forest Networks for Domain Generalization and Visual Recognition [ICLR 2020] (GCFN, ensemble learning, self-supervised learning)
[127] Domain Generalization via Semi-supervised Meta Learning [arXiv 2020] [Code] (DGSML, meta-learning, semi/weak/un-supervised domain generalization)
[128] Heterogeneous Domain Generalization via Domain Mixup [ICASSP 2020] [Code] (data augmentation, open/heterogeneous domain generalization)
[129] NAS-OoD Neural Architecture Search for Out-of-Distribution Generalization [ICCV 2021] (NAS-OoD, neural architecture search)
[130] A Style and Semantic Memory Mechanism for Domain Generalization [ICCV 2021] (STEAM, self-supervised learning, causality)
[131] Learning Transferrable and Interpretable Representations for Domain Generalization [MM 2021] (DTN, ensemble learning)
[132] Adaptive Methods for Real-World Domain Generalization [CVPR 2021] [Code] (DA-ERM, inference-time)
[133] Confidence Calibration for Domain Generalization Under Covariate Shift [ICCV 2021] (domain alignment)
[134] In Search of Lost Domain Generalization [ICLR 2021] (theory & analysis)
[135] The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization [ICCV 2021] [Code] (theory & analysis)
[136] Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization [NeurIPS 2021] [Code] (T3A, inference-time)
[137] Feature Stylization and Domain-aware Contrastive Learning for Domain Generalization [MM 2021] (data augmentation, self-supervised learning)
[138] SelfReg: Self-Supervised Contrastive Regularization for Domain Generalization [ICCV 2021] (SelfReg, self-supervised learning, regularization)
[139] Domain Generalisation with Domain Augmented Supervised Contrastive Learning [AAAI Student Abstract 2021] (DASCL, data augmentation, self-supervised learning)
[140] Invariant Information Bottleneck for Domain Generalization [AAAI 2022] [Code] (IIB, information, causality)
[141] Progressive Domain Expansion Network for Single Domain Generalization [CVPR 2021] [Code] (PDEN, domain alignment, self-supervised learning, information, single domain generalization)
[142] A Simple Feature Augmentation for Domain Generalization [ICCV 2021] (SFA, data augmentation)
[143] Domain-Invariant Disentangled Network for Generalizable Object Detection [ICCV 2021] (disentangled representation learning)
[144] Multi-Domain Adversarial Feature Generalization for Person Re-Identification [TIP 2021] (MMFA-AAE, domain alignment, self-supervised learning, person re-identification)
[145] Learning Causal Semantic Representation for Out-of-Distribution Prediction [NeurIPS 2021] [Code] (CSG-ind, causality)
[146] Domain Generalization via Feature Variation Decorrelation [MM 2021] (disentangled representation learning)
[147] FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space [CVPR 2021] [Code] (FedDG, data augmentation, self-supervised learning, federated domain generalization)
[148] Domain Generalization via Gradient Surgery [ICCV 2021] [Code] (Agr, regularization)
[149] Shape-Biased Domain Generalization via Shock Graph Embeddings [ICCV 2021] (disentangled representation learning)
[150] Universal Cross-Domain Retrieval Generalizing Across Classes and Domains [ICCV 2021] [Code] (SnMpNet, data augmentation, open/heterogeneous domain generalization)
[151] Out-of-domain Generalization from a Single Source: A Uncertainty Quantification Approach [arXiv 2021] (data augmentation, self-supervised learning, single domain generalization)
[152] Recovering Latent Causal Factor for Generalization to Distributional Shifts [NeurIPS 2021] [Code] (LaCIM, causality)
[153] Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning [CVPR 2021] (Meta-DR, data augmentation, meta-learning, life-long learning)
[154] On Calibration and Out-of-domain Generalization [NeurIPS 2021] (domain alignment, causality)
[155] Generalizing to Unseen Domains: A Survey on Domain Generalization [IJCAI 2021] [Slides] (survey)
[156] Better Pseudo-label Joint Domain-aware Label and Dual-classifier for Semi-supervised Domain Generalization [arXiv 2021] (data augmentation, semi/weak/un-supervised domain generalization)
[157] Embracing the Dark Knowledge: Domain Generalization Using Regularized Knowledge Distillation [MM 2021] (KDDG, ensemble learning, regularization)
[158] Learning To Diversify for Single Domain Generalization [ICCV 2021] [Code] (information, single domain generalization)
[159] Collaborative Optimization and Aggregation for Decentralized Domain Generalization and Adaptation [ICCV 2021] (COPDA, normalization, federated domain generalization)
[160] A Fourier-Based Framework for Domain Generalization [CVPR 2021] [Code] (FACT, data augmentation, regularization)
[161] Collaborative Semantic Aggregation and Calibration for Separated Domain Generalization [arXiv 2021] [Code] (CSAC, domain alignment, federated domain generalization)
[162] Domain-Specific Bias Filtering for Single Labeled Domain Generalization [arXiv 2021] [Code] (DSBF, semi/weak/un-supervised domain generalization)
[163] Learning Domain-Invariant Relationship with Instrumental Variable for Domain Generalization [arXiv 2021] (DRIVE, causality)
[164] Adaptation and Generalization Across Domains in Visual Recognition with Deep Neural Networks [PhD 2020] (other resources)
[165] Invariant Risk Minimization [arXiv 2019] [Code] (IRM, regularization, causality)
[166] Beyond Domain Adaptation: Unseen Domain Encapsulation via Universal Non-volume Preserving Models [arXiv 2018] (UNVP, domain alignment)
[167] Multi-component Image Translation for Deep Domain Generalization [WACV 2019] [Code] (data augmentation)
[168] Uncertainty-guided Model Generalization to Unseen Domains [CVPR 2021] [Code] (data augmentation, meta-learning, single domain generalization)
[169] Image Alignment in Unseen Domains via Domain Deep Generalization [arXiv 2019] (DeGIA, domain alignment)
[170] Towards Principled Disentanglement for Domain Generalization [arXiv 2021] [Code] (DDG, data augmentation, disentangled representation learning)
[171] DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic Augmentation [AAAI 2021] [Code] (DecAug, data augmentation, disentangled representation learning)
[172] Domain Generalization for Mammography Detection via Multi-style and Multi-view Contrastive Learning [MICCAI 2021] [Code] (MSVCL, self-supervised learning)
[173] Fishr: Invariant Gradient Variances for Our-of-distribution Generalization [arXiv 2021] [Code] (Fishr, regularization)
[174] Dynamically Decoding Source Domain Knowledge for Unseen Domain Generalization [arXiv 2021] (D2SDK, ensemble learning)
[175] Class-conditioned Domain Generalization via Wasserstein Distributional Robust Optimization [ICLR workshop 2021] (ensemble learning)
[176] Domain and Content Adaptive Convolution for Domain Generalization in Medical Image Segmentation [arXiv 2021] (DCAC, ensemble learning)
[177] Scale Invariant Domain Generalization Image Recapture Detection [ICONIP 2021] (SADG, domain alignment, self-supervised learning)
[178] Unsupervised Domain Generalization by Learning a Bridge Across Domains [arXiv 2021] (self-supervised learning, semi/weak/un-supervised domain generalization)
[179] Semi-Supervised Domain Generalization in RealWorld: New Benchmark and Strong Baseline [arXiv 2021] (domain alignment, semi/weak/un-supervised domain generalization)
[180] Few-Shot Classification in Unseen Domains by Episodic Meta-Learning Across Visual Domains [ICIP 2021] (x-EML, meta-learning)
[181] Energy-based Out-of-distribution Detection [NeurIPS 2020] [Code] (regularization)
[182] ROBIN : A Benchmark for Robustness to Individual Nuisances in Real-World Out-of-Distribution Shifts [arXiv 2021] (ROBIN dataset) [Code]
[183] Towards Non-I.I.D. Image Classification: A Dataset and Baselines [PR 2021] (NICO dataset)
[184] More is Better: A Novel Multi-view Framework for Domain Generalization [arXiv 2021] (data augmentation, meta-learning)
[185] Meta-Learned Feature Critics for Domain Generalized Semantic Segmentation [ICIP 2021] (meta-learning, disentangled representation learning)
[186] Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition [WACV 2022] (RNA-Net, normalization)
[187] Generalizable Person Re-identification with Relevance-aware Mixture of Experts [CVPR 2021] (RaMoE, ensemble learning, person re-identification)
[188] Domain Generalization by Marginal Transfer Learning [JMLR 2021] [Code] (theory & analysis, data augmentation)
[189] Feature Alignment and Restoration for Domain Generalization and Adaptation [arXiv 2020] (FAR, domain alignment)
[190] Out-of-Distribution Generalization via Risk Extrapolation [ICML 2021] (REx, regularization)
[191] A Causal Framework for Distribution Generalization [TPAMI 2021] [Code] (NILE, causality)
[192] Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments [arXiv 2021] (domain alignment)
[193] Robustnet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening [CVPR 2021] [Code] (RobustNet, disentangled representation learning)
[194] Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencoder [ICCV 2021] (NSAE, self-supervised learning)
[195] Domain Generalization under Conditional and Label Shifts via Variational Bayesian Inference [IJCAI 2021] (VBCLS, domain alignment)
[196] The Risks of Invariant Risk Minimization [ICLR 2021] (theory & analysis)
[197] VideoDG: Generalizing Temporal Relations in Videos to Novel Domains [TPAMI 2021] [Code] (APN, data augmentation)
[198] An Empirical Investigation of Domain Generalization with Empirical Risk Minimizers [NeurIPS 2021] [Code] (theory & analysis)
[199] Towards a Theoretical Framework of Out-Of-Distribution Generalization [NeurIPS 2021] (theory & analysis)
[200] Model-Based Domain Generalization [NeurIPS 2021] [Code] (MBDG, data augmentation, regularization)
[201] Swad: Domain Generalization by Seeking Flat Minima [NeurIPS 2021] [Code] (SWAD, regularization)
[202] Exploiting Domain-Specific Features to Enhance Domain Generalization [NeurIPS 2021] [Code] (mDSDI, meta-learning, disentangled representation learning, information)
[203] Adversarial Teacher-Student Representation Learning for Domain Generalization [NeurIPS 2021] (data augmentation, self-supervised learning)
[204] Training for the Future: A Simple Gradient Interpolation Loss to Generalize Along Time [NeurIPS 2021] [Code] (GI, regularization)
[205] Out-of-Distribution Generalization in Kernel Regression [NeurIPS 2021] (theory & analysis)
[206] Quantifying and Improving Transferability in Domain Generalization [NeurIPS 2021] [Code] (theory & analysis, regularization)
[207] Invariance Principle Meets Information Bottleneck for Out-Of-Distribution Generalization [NeurIPS 2021] [Code] (IB-IRM, information, causality)
[208] TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification [NeurIPS 2021] [Code] (TransMatcher, ensemble learning, person re-identification)
Feel free to contribute to our repository.
- If you woulk like to correct mistakes, please do it directly;
- If you would like to add/update papers, please finish the following tasks (if necessary):
- Update Paper Index.
- Update Papers.
- Update Datasets with reference of Paper Index.
- If you have any questions or advice, please contact us by email (yuanjk@zju.edu.cn) or GitHub issues.
Thank you for your cooperation and contributions!
- We refer to awesome-domain-adaptation to design the hierarchy of the Contents.
- We refer to [3] to design the Contents and the table of Datasets.